Knowledge Injection via XAI: Predicting OOD Robustness¶

Parameter-Efficient Fine-Tuning with LoRA Adapters on DINOv2¶

Research Question: Can Explainability (XAI) metrics computed on clean images predict model robustness under Out-of-Distribution (OOD) corruptions?

Hypothesis: Attention-based XAI metrics (Entropy, Deletion Score) extracted from clean images serve as reliable early indicators of model robustness under distribution shift.

Table of Contents¶

1. Configuration and Data Loading
2. Medallion Architecture Pipeline
   • Bronze Layer: Distributed Feature Extraction
   • Silver Layer: XAI Metrics Computation
   • OOD Layer: Corruption-Based Robustness Testing
   • Gold Layer: Correlation Analysis and Meta-Learner
3. Adapter Zoo: LoRA Training
4. XAI Metrics Framework
5. OOD Corruption Strategy
6. Robustness Analysis
7. XAI-Robustness Correlations
8. Meta-Learner Performance
9. Feature Importance Analysis
10. Conclusions

Loaded 10 Gold Layer datasets
Training metrics: 3 adapter(s)
Available datasets: ['correlations', 'classifier_comparison', 'feature_importance', 'adapter_summary', 'degradation', 'qualitative_summary', 'quantitative_summary', 'xai_feature_ranking', 'adapter_ranking', 'worst_corruption']

2. Medallion Architecture Pipeline¶

The experimental pipeline follows a Medallion Architecture (Bronze - Silver - Gold) with a dedicated OOD evaluation layer, implemented using Apache Spark for distributed processing.

2.1 Bronze Layer: Distributed Feature Extraction¶

Purpose: Extract embeddings from raw images using DINOv2 backbone with Spark Pandas UDFs.

# Key implementation (bronze_layer.py)
model = AutoModel.from_pretrained(
    "facebook/dinov2-base",
    torch_dtype=torch.float16,
    attn_implementation="sdpa"  # Scaled Dot-Product Attention
)

2.2 Silver Layer: Distributed XAI Extraction¶

Purpose: Apply LoRA adapters and compute explainability metrics on clean images.

2.3 OOD Layer: Corruption-Based Robustness Testing¶

Purpose: Evaluate adapter robustness under controlled image corruptions.

Output: Binary is_correct label per (image, adapter, corruption) tuple.

2.4 Gold Layer: Correlation Analysis and Meta-Learner¶

Purpose: Validate hypothesis and train Meta-Learner to predict robustness from XAI metrics.

3. Adapter Zoo: LoRA Training¶

Parameter-Efficient Fine-Tuning (PEFT) with LoRA¶

The Adapter Zoo contains three Low-Rank Adaptation (LoRA) adapters with varying capacities, trained on the DINOv2-base backbone.

LoRA Configuration:

• Technique: DoRA (Weight-Decomposed LoRA) + RsLoRA (Rank-Stabilized)
• Alpha Scaling: $\alpha = 2 \times r$ (scaling factor)
• Target Modules: query, value, fc1, fc2 (attention + MLP layers)
• Dropout: 0.1

Training Hyperparameters:

• Optimizer: AdamW with learning rate $3 \times 10^{-4}$
• Epochs: 15 with gradient accumulation (factor 2)
• Batch Size: 16 (effective 32 with accumulation)
• Regularization: Dropout = 0.1, DoRA + RsLoRA enabled
• Target Modules: query, value, fc1, fc2

Data Augmentation:

• Random rotation (30 degrees)
• Horizontal flip (p=0.5)
• Color jitter (brightness/contrast 0.2)
• Random crop (224x224 from 256x256)

LoRA Adapter Training Results
================================================================================

4. XAI Metrics Framework¶

The XAI framework computes four complementary metrics from attention maps to assess model interpretability and predict robustness.

Metric Definitions¶

1. Attention Entropy (normalized Shannon entropy)

Where $p_i$ is the attention weight for patch $i$, normalized to $[0, 1]$.

• High entropy = Dispersed, unfocused attention
• Low entropy = Concentrated, focused attention

2. Sparsity (Gini Coefficient)

Where $p_{(i)}$ are sorted attention weights.

• High sparsity = Attention concentrated on few patches
• Low sparsity = Attention distributed across many patches

3. Deletion Score (Faithfulness Metric from RISE)

Progressively remove patches in order of importance (highest attention first) and measure AUC of confidence drop:

• Lower score = Attention correctly identifies important regions

4. Insertion Score (Faithfulness Metric)

Progressively reveal patches starting from blank image and measure AUC of confidence recovery:

• Higher score = Attention correctly identifies important regions

5. OOD Corruption Strategy¶

Corruption Types and Severity Levels¶

The OOD Layer applies three corruption types at three severity levels to stress-test adapter robustness under distribution shift.

Each corruption simulates real-world image degradation scenarios:

• Gaussian Noise: Sensor noise, low-light conditions
• Blur: Motion blur, defocus
• Contrast: Lighting variations, exposure issues

OOD Corruption Configuration
============================================================

6. Robustness Analysis¶

6.1 Adapter Performance on OOD Data¶

How do the adapters from the Adapter Zoo perform under corrupted images? Lower-rank adapters are expected to generalize better due to implicit regularization.

Adapter Zoo: OOD Performance Summary
================================================================================

Key Findings:
  - Best OOD robustness:  Rank 4 (95.0%)
  - Worst OOD robustness: Rank 32 (75.9%)
  - Performance gap: 19.1 percentage points

6.2 Accuracy Degradation by Corruption¶

How much does accuracy drop from shallow to heavy corruption for each type?

Degradation Statistics
============================================================
Max drop:     81.1%
Min drop:     0.4%
Mean drop:    30.5%

Worst case:   Rank 32 + blur (81.1% drop)

6.3 XAI Metrics Distribution by Adapter¶

7. XAI-Robustness Correlations¶

Core Research Question: Do XAI metrics on clean images predict failures on corrupted images?

Statistical Measures¶

XAI Feature Correlations with OOD Robustness
================================================================================

Interpretation Guide:
  - Negative r (entropy): Higher entropy = LESS robust
  - Positive r (insertion): Higher score = MORE robust
  - Cohen's d > 0.5: Medium effect size (meaningful difference)

8. Meta-Learner Performance¶

Meta-Learner Design¶

The meta-learner predicts whether a sample will be correctly classified under corruption, using only XAI features from clean images.

Training Configuration:

• Input: 4 XAI features (entropy, sparsity, deletion_score, insertion_score)
• Target: Binary label (is_correct under corruption)
• Split: 80% train / 20% test, stratified
• Scaling: StandardScaler on features
• Validation: 5-Fold Stratified Cross-Validation

Models Compared:

Meta-Learner Performance Comparison
================================================================================

Best Model: XGBoost_Tuned (ROC-AUC: 0.739)

9. Feature Importance Analysis¶

Which XAI metrics contribute most to robustness prediction?

Feature Importance Ranking
================================================================================

Importance Measures:
  - XGB Importance: Gain-based importance from XGBoost
  - Permutation: Drop in accuracy when feature is shuffled
  - LR Odds Ratio: exp(coefficient) from LogisticRegression

10. Summary and Conclusions¶

10.1 Qualitative and Quantitative Summary¶

QUALITATIVE SUMMARY
============================================================

QUANTITATIVE SUMMARY
============================================================

WORST CORRUPTION PER ADAPTER
============================================================

================================================================================
                            KEY RESEARCH FINDINGS
================================================================================

1. XAI METRICS PREDICT ROBUSTNESS

   * Entropy (r=-0.17): Higher entropy indicates less robust predictions
   * Insertion Score (r=+0.18): Best positive predictor of robustness
   * Cohen's d up to 0.55: Medium effect size confirms practical significance

2. ADAPTER RANK MATTERS

   * Rank 4:  Best OOD robustness (~95%) despite fewer parameters
   * Rank 32: Worst OOD robustness (~76%) - evidence of OVERFITTING
   * Conclusion: Lower rank = better generalization to corrupted data

3. CORRUPTION IMPACT VARIES SIGNIFICANTLY

   * Blur:     Most devastating (up to 81% accuracy drop at heavy level)
   * Gaussian: Moderate impact (~41% drop at heavy level)
   * Contrast: Minimal impact (<1% drop even at heavy level)

4. META-LEARNER ACHIEVES PREDICTIVE POWER

   * XGBoost ROC-AUC: ~0.74 (predicting failures from clean-image XAI metrics)
   * Validation: Hypothesis CONFIRMED - XAI metrics can predict OOD robustness

================================================================================

10.2 Conclusions¶

Hypothesis Validation: CONFIRMED

1. XAI metrics computed on clean images CAN predict OOD robustness (ROC-AUC ~0.74)

2. Entropy is the most informative metric - models with higher attention entropy are less robust under corruption

3. Lower LoRA rank generalizes better - Rank 4 outperforms Rank 32 on corrupted data despite having 6x fewer parameters

4. Blur is the most challenging corruption - up to 81% accuracy drop, while contrast changes are almost harmless

5. Practical application: Use XAI metrics as early warning system for robustness issues before deployment

Future Work¶

• Extend to additional corruption types (JPEG compression, weather effects)
• Test on other vision backbones (ConvNeXt, CLIP)
• Investigate per-class robustness patterns
• Deploy meta-learner as real-time monitoring tool